{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VRP2V7XBPDSO3P7CRAV72B77JN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"de01409763cd7a7a51403426225467a968bac4a5952e3013f9a6c3b97be4122a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T14:14:44Z","title_canon_sha256":"78e8bba7a94a5c70bb9a2673727516c3edbb08e5bf68bc475b4b7e43a505b78a"},"schema_version":"1.0","source":{"id":"2607.22708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22708","created_at":"2026-07-28T00:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22708v1","created_at":"2026-07-28T00:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22708","created_at":"2026-07-28T00:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"VRP2V7XBPDSO","created_at":"2026-07-28T00:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"VRP2V7XBPDSO3P7C","created_at":"2026-07-28T00:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"VRP2V7XB","created_at":"2026-07-28T00:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:59547d1b8af49b8e392903c3a7433991d9efd1234b4956493fe0b2b742efd469","target":"graph","created_at":"2026-07-28T00:21:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.22708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deploying a vision-language model with full UI understanding on end devices has long been trapped between accuracy and efficiency: on one side is the accuracy bar for OCR, screen understanding, visual question answering, and element grounding; on the other is the strict compute, memory, and power budget of mobile chips. Existing work either trades one for the other, or stops at simulation without real-device validation. We present StepX-Edge, a 0.9B-parameter on-device UI vision-language model that resolves this tension through three-layer co-design of architecture, training, and deployment. A","authors_text":"Fanyi Wang, Haotian Hu, Jineng Han, Liujian Tang, Wentao Qiu, Yin Wang, Zhenhua Ge","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T14:14:44Z","title":"StepX-Edge: An On-Device UI Vision-Language Model via Architecture-Training-Deployment Co-Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22708","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9182d57f7c87561c8b5c6f5d0391786d994e3effb3727a909170be522ff7f829","target":"record","created_at":"2026-07-28T00:21:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"de01409763cd7a7a51403426225467a968bac4a5952e3013f9a6c3b97be4122a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T14:14:44Z","title_canon_sha256":"78e8bba7a94a5c70bb9a2673727516c3edbb08e5bf68bc475b4b7e43a505b78a"},"schema_version":"1.0","source":{"id":"2607.22708","kind":"arxiv","version":1}},"canonical_sha256":"ac5faafee178e4edbfe2882bfd07ff4b564693f2dbdee742ce60c3dc7dd395c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac5faafee178e4edbfe2882bfd07ff4b564693f2dbdee742ce60c3dc7dd395c9","first_computed_at":"2026-07-28T00:21:50.269285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:50.269285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dUhAw9gjjgwnJFi3u9FPyEvkAMkTjvrfvZG6C6P/XoY4yGCt2Yndc2yFHxkO3OBQnEvvGHE92OKysRES6B5zDw==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:50.270170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9182d57f7c87561c8b5c6f5d0391786d994e3effb3727a909170be522ff7f829","sha256:59547d1b8af49b8e392903c3a7433991d9efd1234b4956493fe0b2b742efd469"],"state_sha256":"1d81365bf7ae4a00079e66cc07a500abf700502043270d87c67faa21ba265a23"}